© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 19-RESID-POST-AA · 21410 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
19-RESID-POST-AA
21410

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0

Dataset (Dashboard)

Various

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 switch

-0.08

oplevel

-0.08

 goose

-0.08

Always

-0.08

 instinct

-0.08

 useless

-0.08

Switch

-0.07

	switch

-0.07

_switch

-0.07

 মুহ

-0.07

POSITIVE LOGITS

 모집

0.21

 recruited

0.19

 recruitment

0.18

 selection

0.18

 purpos

0.17

 Selection

0.17

 Recruitment

0.17

 criteria

0.17

selection

0.17

 선정

0.16

Activations Density 0.018%

No Known Activations